
import matplotlib.pyplot as plt
import pandas as pd
from matplotlib.lines import Line2D
import seaborn as sns
import numpy as np
import random
import matplotlib.pyplot as plt
import pandas as pd
from matplotlib.lines import Line2D
import seaborn as sns

df = pd.read_csv("local/ejemplo2.csv")


#https://matplotlib.org/stable/gallery/lines_bars_and_markers/categorical_variables.html
def colors_from_labels(label):
    if label in ["Must Have","Fix ASAP"]:
        return "red"
    elif label in ["Fix", "Good"]:
        return "orange"
    elif label in ["Nice to Have","Fix if Time"]:
        return "green"
        
colors = list(map(colors_from_labels, df.loc[:,"Priority"].values))
tipos = df.loc[:,"Task Type"].values
esfuerzos = 75*df.loc[:,"Effort"].values
tiempos = df.loc[:,"Time"].values
fig, axs = plt.subplots(1, 1, figsize=(8, 8))
legend_elements = [Line2D([0], [0], marker='o', color='w', label='High priority',
                          markerfacecolor="red", markersize=15),
                   Line2D([0], [0], marker='o', color='w', label='Medium priority',
                          markerfacecolor="orange", markersize=15),
                  Line2D([0], [0], marker='o', color='w', label='Low priority',
                          markerfacecolor="green", markersize=15)]

axs.legend(handles=legend_elements, frameon=False, loc="upper right")
axs.scatter(x = tipos, y = tiempos,s = esfuerzos, color = colors, edgecolors='black')

axs.set_ylabel("Time in days")
axs.set_xlabel("Software task type")
axs.set_title('Software development task priorities (bigger dot size: more difficulty)', pad=30)
axs.set_xlim([-0.5,2.5])
axs.set_ylim([0, max(tiempos)+5])
plt.tight_layout()
plt.text(x=-0.5, y=-8, s='Grafica realizada por Matias Macias y Alberto M. Ceballos', fontsize=15, alpha=0.75, va='bottom')
plt.show()


import seaborn as sns
import numpy as np

sns.set(style='ticks', context='talk')
def sizes_from_labels(label):
    if label in ["Must Have","Fix ASAP"]:
        sz = 750
    elif label in ["Fix", "Good"]:
        sz = 250
    elif label in ["Nice to Have","Fix if Time"]:
        sz = 100
    return sz

def colors_from_labels(label):
    if label == "Bug":
        return "red"
    elif label == "Feature":
        return "lightblue"
    elif label == "User Story":
        return "gray"
        
colors = list(map(colors_from_labels, df.loc[:,"Task Type"].values))
tipos = df.loc[:,"Task Type"].values
tiempos = df.loc[:,"Time"].values
esfuerzos = df.loc[:,"Effort"].values
sizes = list(map(sizes_from_labels, df.loc[:,"Priority"].values))


fig, axs = plt.subplots(1, 1, figsize=(8, 8))
axs.scatter(x = esfuerzos, y = tiempos, color = colors, s = sizes, edgecolors='black')
axs.set_ylabel("Time in days")
axs.set_xlabel("Effort in points")
axs.set_title('Software development task priorities (bigger dot size: more priority)', pad=30)
legend_elements = [Line2D([0], [0], marker='o', color='w', label='Bug',
                          markerfacecolor="red", markersize=15),
                   Line2D([0], [0], marker='o', color='w', label='User Story',
                          markerfacecolor="gray", markersize=15),
                  Line2D([0], [0], marker='o', color='w', label='Feature',
                          markerfacecolor="lightblue", markersize=15)]
axs.legend(handles=legend_elements, frameon=False)
plt.tight_layout()
axs.text(x=0.5, y=-7, s='Grafica realizada por Matias Macias y Alberto M. Ceballos', fontsize=15, alpha=0.75, va='bottom')
plt.show()


sns.set(style='ticks', context='talk')

def obtener_productividad(x):
    if x < 0.7:
        return 90 + random.random()
    else:
        return 90 - x**2 + random.random()
    
x_mat = np.linspace(0, 4, 40)
x = np.array(list(range(0, 40, 1)))
productividad = np.array(list(map(obtener_productividad, x_mat)))

empleados_base = [125]*5
for i in range(35):
    empleados_base.append(empleados_base[-1]+random.randint(0,5))

    
empleados_base = np.array(empleados_base)
fig = plt.figure(figsize=(16,8))
plt.fill_between(x+1, productividad - empleados_base**3/6000000, productividad + empleados_base**3/60000000, label = "Grosor: cantidad de empleados")
plt.plot(x+1,productividad-0.15, color = 'orange', linewidth = 1.5, label = "Tendencia de la productividad")
plt.title("Cambio en productividad con las semanas y el aumento en la contratación", pad=30)
plt.xlabel("Semanas")
sns.despine()
plt.ylabel("Productividad (%)")
plt.axvline(x = 10, linewidth=1.4, color='black', label="Cambio en la administración", linestyle='--')
plt.xlim(1,40)
plt.legend(frameon=False)
plt.text(x=1, y=68.5, s='Grafica realizada por Matias Macias y Alberto M. Ceballos', fontsize=14, alpha=0.75, va='bottom')
plt.show()


def obtener_productividad(x):
    if x < 0.7:
        return 90 + random.random()
    else:
        return 90 - x**2 + random.random()
    
x_mat = np.linspace(0, 4, 40)
tiempo = np.array(list(range(0, 40, 1)))
productividad = np.array(list(map(obtener_productividad, x_mat)))

empleados_base = [125]*5
for i in range(35):
    empleados_base.append(empleados_base[-1]+random.randint(0,2))
    
tiempo = list(tiempo)
tiempo = ["Anterior gerencia" if ti <= 10 else "Nueva gerencia" for ti in tiempo]


fig = plt.figure(dpi=100, figsize=(6,6))
sns.scatterplot(x=empleados_base, y = productividad, hue = tiempo)
sns.despine()
plt.title("La nueva gerencia sigue perdiendo productividad\n independiente de la cantidad de empleados", pad=30)
plt.xlabel("Número de empleados")
plt.ylabel("Productividad (%)")
plt.legend(frameon=False, bbox_to_anchor=(1.6, 1))
plt.text(x=110, y=70, s='Grafica realizada por Matias Macias y Alberto M. Ceballos', fontsize=10, alpha=0.75, va='bottom')
plt.show()


import pandas as pd
df = pd.read_json("local/penguins.json")
df_2 = df.dropna()
df_2


df_2.Sex.unique()

array(['MALE', 'FEMALE', '.'], dtype=object)


np.unique(df_2["Sex"].values)
df_2 = df_2[df_2["Sex"]!="."]


df_2.describe()


def view_frequencies(ax, df, variable, title):
    df = df.copy()
    df.loc[:,"Frequency"] = 1
    df_grp = df[[variable,"Frequency"]].groupby(variable).count().reset_index()
    df_grp["Frequency"]*=100/len(df)
    sns.barplot(ax = ax, x=df_grp[variable], y=df_grp.Frequency)
    ax.set_ylabel("Frequency (%)")
    ax.set_ylim(0,60)
    #show_values_on_bars_float(ax)
    ax.set_title(title)
    
fig, ax = plt.subplots(1,1, figsize=(8,6),dpi = 100)
view_frequencies(ax, df, "Species", title=False)
ax.set_title(f"Relative freq. of species among the {len(df_2)} penguins in the dataset", pad=30)
plt.text(x=-0.6, y=-15, s='Grafica realizada por Matias Macias y Alberto M. Ceballos', fontsize=10, alpha=0.75, va='bottom')
plt.tight_layout()


fig, ax = plt.subplots(1,1, figsize=(8, 6),dpi = 100)
view_frequencies(ax, df_2, "Island", title=False)
ax.set_title(f"% of penguins per island among the {len(df_2)} penguins in the dataset", pad=30)
plt.text(x=-0.6, y=-15, s='Grafica realizada por Matias Macias y Alberto M. Ceballos', fontsize=10, alpha=0.75, va='bottom')
plt.tight_layout()


fig, ax = plt.subplots(1,1, figsize=(6,6),dpi = 100)
view_frequencies(ax, df_2, "Sex", title=False)
ax.set_title(f"% of penguins per sex among the {len(df_2)} penguins in the dataset", pad=30)
plt.text(x=-0.6, y=-15, s='Grafica realizada por Matias Macias y Alberto M. Ceballos', fontsize=10, alpha=0.75, va='bottom')
plt.tight_layout()


num_variables = ["Beak Length (mm)","Beak Depth (mm)","Flipper Length (mm)","Body Mass (g)"]


fig, axes = plt.subplots(1,4, figsize=(16,6), dpi = 300)
axes = axes.flatten()
colors = ["blue","orange","green","magenta"]
plt.text(x=-0.6, y=-20, s='Grafica realizada por Matias Macias y Alberto M. Ceballos', fontsize=12, alpha=0.75, va='bottom')
for i, var in enumerate(num_variables):
    sns.histplot(df_2[var], ax = axes[i], color = colors[i], kde = True)
    axes[i].set_ylabel("Frequency")
plt.suptitle("Histograms of all numerical variables")
plt.tight_layout()


fig, axes = plt.subplots(2,3, figsize=(12,8), dpi = 100)
axes = axes.flatten()
num_variables = ["Beak Length (mm)","Beak Depth (mm)","Flipper Length (mm)","Body Mass (g)"]
ax_id = 0
colors = ["blue","magenta","orange","black","darkgreen","gray"]
for i in range(4):
    for j in range(i+1, 4):
        axes[ax_id].set_title(num_variables[i].split(" (")[0] + " vs " + num_variables[j].split(" (")[0])
        sns.regplot(x = df_2[num_variables[i]], y=df_2[num_variables[j]], ax = axes[ax_id], color = colors[ax_id])
        ax_id+=1
        
plt.suptitle("Comparisons between numerical variables in the penguins dataset")
plt.tight_layout()
plt.text(x=0, y=0,s='Grafica realizada por Matias Macias y Alberto M. Ceballos', fontsize=12, alpha=0.75)
plt.show()


df_view = df_2.copy()

fig, axes = plt.subplots(2,3, figsize=(18,12), dpi = 300)
axes = axes.flatten()
num_variables = ["Beak Length (mm)","Beak Depth (mm)","Flipper Length (mm)","Body Mass (g)"]
ax_id = 0
for i in range(4):
    for j in range(i+1, 4):

        axes[ax_id].set_title(num_variables[i].split(" (")[0] + " vs " + num_variables[j].split(" (")[0])
        sns.scatterplot(x = df_view[num_variables[i]], y=df_view[num_variables[j]], hue = df_view["Species"],ax = axes[ax_id])
        axes[ax_id].get_legend().set_visible(False)
        ax_id+=1
        
handles, labels = axes[0].get_legend_handles_labels()
fig.legend(handles, labels, loc='upper left', frameon=False, bbox_to_anchor=(1.05, 1), fontsize=30)
plt.suptitle("Scatterplot of numerical attributes by species")

plt.tight_layout()
plt.text(x=0, y=100,s='Grafica realizada por Matias Macias y Alberto M. Cebayos', fontsize=20, alpha=0.75)
plt.show()


df_view = df_2.copy()
df_view.loc[:,"Frequency"] = 1
df_view = df_view[["Island","Species","Frequency"]].groupby(["Island","Species"]).count().reset_index()

df_view.loc[len(df_view)] = ["Biscoe","Chinstrap",0]
df_view.loc[len(df_view)] = ["Dream","Gentoo",0]
df_view.loc[len(df_view)] = ["Torgersen","Chinstrap",0]
df_view.loc[len(df_view)] = ["Torgersen","Gentoo",0]


fig, ax = plt.subplots(1,1, figsize=(16,6), dpi = 100)
sns.barplot(x=df_view["Island"], y = df_view["Frequency"], hue = df_view["Species"],ax = ax)
sns.despine()
plt.title("Counts of penguin species per island")
plt.legend(frameon=False)
ax.set_ylim(0,150)
ax.set_ylabel("Amount of Penguins per island")
ax.set_ylabel("Island")
plt.text(x=-0.5, y=-25, s='Grafica realizada por Matias Macias y Alberto M. Ceballos', fontsize=12, alpha=0.75, va='bottom')
plt.show()


df = pd.read_json("local/ticket_trend.json")
df.head()


from datetime import datetime

date = pd.datetime(2019, 5, 1)
date

<ipython-input-400-189e2b1f63c9>:3: FutureWarning: The pandas.datetime class is deprecated and will be removed from pandas in a future version. Import from datetime module instead.
  date = pd.datetime(2019, 5, 1)

datetime.datetime(2019, 5, 1, 0, 0)


fig = plt.figure(dpi = 300, figsize=(12,4))
sns.lineplot(x=df["Date"], y = df["Number_of_Tickets"], hue = df["Ticket_Type"])

sns.despine()
plt.ylabel("Tickets")
plt.axvline(x = date, linewidth=1.4, color='black', label="Cambio en la administración", linestyle='--')
plt.legend(frameon=False, loc='upper right', bbox_to_anchor=(1.1, 1))
plt.title("La perdida de empleados esta generando una disminucion \n en la capacida de procesamiento de los tickets",pad=30)
plt.text(x= datetime(2018,12,1), y=50, s='Grafica realizada por Matias Macias y Alberto M. Ceballos', fontsize=10, alpha=0.75)
plt.show()


import datetime
ratio = (100*df[df["Ticket_Type"]=="Processed"]["Number_of_Tickets"].values/df[df["Ticket_Type"]=="Received"]["Number_of_Tickets"].values).astype(np.uint8)
dates  = df[df["Ticket_Type"]=="Received"]["Date"].values

fig = plt.figure(dpi = 300, figsize=(12,4))
sns.lineplot(x=dates[0:5], y = ratio[0:5])
sns.lineplot(x=dates[4:], y = ratio[4:], color = "darkred")

sns.despine()
plt.ylabel("% of processed tickets")
plt.axvline(x = date, linewidth=1.4, color='black', label="Perdida de dos empleados", linestyle='--')
plt.title("We need two more people to recover our previous ticket processing capacities", pad=30)
plt.text(date + pd.Timedelta("5 days"), 80, "2 employees\nleft the company", fontsize = 12)
plt.text(x=datetime.date(2018,12,1), y=65, s='Grafica realizada por Matias Macias y Alberto M. Ceballos', fontsize=8, alpha=0.75)
plt.xlabel("Month")
plt.show()
#Datos tomados de x,y,z, los hizo Matias y Alberto.


df = pd.read_json("local/encuestas.json")
df.head()


fig = plt.figure(figsize=(10,10))
g = sns.barplot(x = df["Opinion"], y = df["Percentage"], hue = df["When"])#.legend_.remove()
sns.despine()
plt.title("Keep investing in programs for getting students interested in science % of students opinion\n \
Before and After the Science Promotion Program", pad=30)
plt.ylabel("% of students with the opinion")
plt.xlabel("Opinion about science")
sns.set_palette("deep")
legend_elements = [Line2D([0], [0], marker= 's',color='w', label='Before Science Promotion Program',
                          markerfacecolor="#5975A4", markersize=25),
                   Line2D([0], [0], marker= 's',color='w', label='After Science Promotion Program',
                          markerfacecolor="#CC8963", markersize=25)]
g.legend(handles = legend_elements, frameon=False, loc='upper left', fontsize=20, bbox_to_anchor=(1.02, 1))
plt.text(x=0.7, y=-6, s='Grafica realizada por Matias Macias y Alberto M. Ceballos', fontsize=14, alpha=0.75, ha='center', va='bottom')

plt.show()

	Species	Island	Beak Length (mm)	Beak Depth (mm)	Flipper Length (mm)	Body Mass (g)	Sex
0	Adelie	Torgersen	39.1	18.7	181.0	3750.0	MALE
1	Adelie	Torgersen	39.5	17.4	186.0	3800.0	FEMALE
2	Adelie	Torgersen	40.3	18.0	195.0	3250.0	FEMALE
4	Adelie	Torgersen	36.7	19.3	193.0	3450.0	FEMALE
5	Adelie	Torgersen	39.3	20.6	190.0	3650.0	MALE
...	...	...	...	...	...	...	...
338	Gentoo	Biscoe	47.2	13.7	214.0	4925.0	FEMALE
340	Gentoo	Biscoe	46.8	14.3	215.0	4850.0	FEMALE
341	Gentoo	Biscoe	50.4	15.7	222.0	5750.0	MALE
342	Gentoo	Biscoe	45.2	14.8	212.0	5200.0	FEMALE
343	Gentoo	Biscoe	49.9	16.1	213.0	5400.0	MALE

	Beak Length (mm)	Beak Depth (mm)	Flipper Length (mm)	Body Mass (g)
count	333.000000	333.000000	333.000000	333.000000
mean	43.992793	17.164865	200.966967	4207.057057
std	5.468668	1.969235	14.015765	805.215802
min	32.100000	13.100000	172.000000	2700.000000
25%	39.500000	15.600000	190.000000	3550.000000
50%	44.500000	17.300000	197.000000	4050.000000
75%	48.600000	18.700000	213.000000	4775.000000
max	59.600000	21.500000	231.000000	6300.000000

	Ticket_Type	Number_of_Tickets	Date
0	Received	160	2019-01-01
1	Received	184	2019-02-01
2	Received	241	2019-03-01
3	Received	149	2019-04-01
4	Received	180	2019-05-01

Ejercicio 2:¶

Ejercicio 3¶

Ejercicio 4:¶

Descripción general¶

Relaciones con variables numéricas:¶

Relaciones de correlación entre las variables numéricas¶

Ejercicio 5¶

VARIABLES:¶

NOTAS:¶

Ejercicio 6¶

Ejercicio 7¶

Insights¶

	Opinion	When	Percentage
0	Bored	Before	11
1	Not great	Before	5
2	Ok	Before	40
3	Kind of interested	Before	25
4	Excited	Before	19